The Classification of Credibility of Thai News Source Websites Using Data Mining Techniques
Keywords:
data mining, data clustering, classification, credibility, online newsAbstract
The increase of unreliability in the online social media nowadays, such as social networking platforms, news blogs and online newspaper websites, causes misunderstanding for the receivers which challenge the news referencing progress. The purpose of this research is to make a model to classify the reliability of Thai-based news references websites. In these terms, this research aims to study the factors and consider the data’s reliability related to each website. Also, the performance comparison of the model, used for classifying progress by collecting the website s’ essential technical data factors and sorting them into groups of data’s references to state the news references’ category, placed the effective ones into 5 groups. Moreover, the data was analyzed by using these 5 analytical techniques: Decision Tree C4.5, Naïve Bayes, K-Nearest Neighbor--K-NN, Multilayer Perceptron and Support Vector Machine--SVM. After being analyzed in performance comparison progress, the K-Nearest Neighbor technique--K-NN, which has the max performance value of 5, 6 and 7, of its K is even (Accuracy=96.03%, Precision =0.962, Recall=0.960, F-measure=0.959). Hence, the researcher chose the K-Nearest Neighbor--KNN technique-when K equals 6 since it would make the analyzation of the 5 groups most effective.
References
Chumwatana, T. (2013). A survey of Automatic Indexing Techniques for Thai Text documents. Information Technology Journal, 9(1), 81-91. (in Thai)
Dumais, S., Platt, J., & Heckerman, D. (1998). Inductive learning algorithm and representation for text categorization. In Conference of Information and Knowledge Management (CIKM) (pp. 148-155). Maryland, USA.: CIKM. doi: 10.1145/288627.288651.
Fairbanks, J., Fitch, N., Knauf, N., & Briscoe, E., (2018). Credibility assessment in the News: Do we need to read?. In Misinformation and Misbehavior Mining on the Web (pp. 1-8). CA., USA.: James P. Fairbanks. http://jpfairbanks.net/publication/mis2-2018/.
Kokkeadtikul, C., & Danphaibun, T., (2018). Fake news: Fake news problems, challenge and policy action. NBTC Journal, 3, 173-192. (in Thai)
Krishnamoorthy, A., Patil, A. K., Vasudevan, N., & Pathari, V. (2018). News article classification with clustering using Semi-Supervised Learning. In International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 86-91). Bangalore, India: ICACCI
Li, J., Fong, S., Zhuang, Y., & Khoury, R. (2016). Hierarchical classification in text mining for sentiment analysis of online news. Soft Computing, 20(9), 3411–3420.
National Statistical Office. (2018). The 2018 household survey on the use of Information and Communication Technology. Bangkok: Economic and Social Statistics Bureau. (in Thai)
Shahi, T., & Pant, A. (2018). Nepali news classification using Naïve Bayes, support vector machines and neural networks. In International Conference on Communication information and Computing Technology (ICCICT) (pp. 1-5). Mumbai, India: ICCICT.
Toommanon, T., & Whattananarong, K. (2012). Creditability and innovation adoption of Online Newspapers. Technical Education Journal King Mongkut’s University of Technology North Bangkok, 3(2), 25-33. (in Thai)
